Add tokenizer config
Browse files- tokenizer_config.json +78 -0
tokenizer_config.json
ADDED
|
@@ -0,0 +1,78 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"backend": "tokenizers",
|
| 4 |
+
"bos_token": null,
|
| 5 |
+
"clean_up_tokenization_spaces": false,
|
| 6 |
+
"eos_token": "<|endoftext|>",
|
| 7 |
+
"errors": "replace",
|
| 8 |
+
"extra_special_tokens": [
|
| 9 |
+
"<|asr|>",
|
| 10 |
+
"<|streaming_asr|>",
|
| 11 |
+
"<|tts|>",
|
| 12 |
+
"<|streaming_tts|>",
|
| 13 |
+
"<|audio_cont_txt|>",
|
| 14 |
+
"<|audio|>",
|
| 15 |
+
"<|audio_end|>",
|
| 16 |
+
"<|text|>",
|
| 17 |
+
"<|text_end|>",
|
| 18 |
+
"<|eoc|>",
|
| 19 |
+
"<|user|>",
|
| 20 |
+
"<|assistant|>",
|
| 21 |
+
"<|system|>",
|
| 22 |
+
"<|await_audio|>",
|
| 23 |
+
"<|ref_audio|>",
|
| 24 |
+
"<|ref_text|>",
|
| 25 |
+
"<|emotion:elation|>",
|
| 26 |
+
"<|emotion:amusement|>",
|
| 27 |
+
"<|emotion:enthusiasm|>",
|
| 28 |
+
"<|emotion:determination|>",
|
| 29 |
+
"<|emotion:pride|>",
|
| 30 |
+
"<|emotion:contentment|>",
|
| 31 |
+
"<|emotion:affection|>",
|
| 32 |
+
"<|emotion:relief|>",
|
| 33 |
+
"<|emotion:contemplation|>",
|
| 34 |
+
"<|emotion:confusion|>",
|
| 35 |
+
"<|emotion:surprise|>",
|
| 36 |
+
"<|emotion:awe|>",
|
| 37 |
+
"<|emotion:longing|>",
|
| 38 |
+
"<|emotion:arousal|>",
|
| 39 |
+
"<|emotion:anger|>",
|
| 40 |
+
"<|emotion:fear|>",
|
| 41 |
+
"<|emotion:disgust|>",
|
| 42 |
+
"<|emotion:bitterness|>",
|
| 43 |
+
"<|emotion:sadness|>",
|
| 44 |
+
"<|emotion:shame|>",
|
| 45 |
+
"<|emotion:helplessness|>",
|
| 46 |
+
"<|env:music|>",
|
| 47 |
+
"<|env:noise|>",
|
| 48 |
+
"<|style:singing|>",
|
| 49 |
+
"<|style:shouting|>",
|
| 50 |
+
"<|style:whispering|>",
|
| 51 |
+
"<|sfx:cough|>",
|
| 52 |
+
"<|sfx:laughter|>",
|
| 53 |
+
"<|sfx:crying|>",
|
| 54 |
+
"<|sfx:screaming|>",
|
| 55 |
+
"<|sfx:burping|>",
|
| 56 |
+
"<|sfx:humming|>",
|
| 57 |
+
"<|sfx:sigh|>",
|
| 58 |
+
"<|sfx:sniff|>",
|
| 59 |
+
"<|sfx:sneeze|>",
|
| 60 |
+
"<|prosody:speed_very_slow|>",
|
| 61 |
+
"<|prosody:speed_slow|>",
|
| 62 |
+
"<|prosody:speed_fast|>",
|
| 63 |
+
"<|prosody:speed_very_fast|>",
|
| 64 |
+
"<|prosody:pitch_low|>",
|
| 65 |
+
"<|prosody:pitch_high|>",
|
| 66 |
+
"<|prosody:pause|>",
|
| 67 |
+
"<|prosody:long_pause|>",
|
| 68 |
+
"<|chatml|>",
|
| 69 |
+
"<|prosody:expressive_high|>",
|
| 70 |
+
"<|prosody:expressive_low|>"
|
| 71 |
+
],
|
| 72 |
+
"is_local": true,
|
| 73 |
+
"model_max_length": 131072,
|
| 74 |
+
"pad_token": "<|endoftext|>",
|
| 75 |
+
"split_special_tokens": false,
|
| 76 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 77 |
+
"unk_token": null
|
| 78 |
+
}
|